XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zichen, Chen, Jianda, Singh, Ambuj, Sra, Misha
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916404583727104
author Chen, Zichen
Chen, Jianda
Singh, Ambuj
Sra, Misha
author_facet Chen, Zichen
Chen, Jianda
Singh, Ambuj
Sra, Misha
contents Large Language Models (LLMs) have achieved remarkable success in natural language tasks, yet understanding their reasoning processes remains a significant challenge. We address this by introducing XplainLLM, a dataset accompanying an explanation framework designed to enhance LLM transparency and reliability. Our dataset comprises 24,204 instances where each instance interprets the LLM's reasoning behavior using knowledge graphs (KGs) and graph attention networks (GAT), and includes explanations of LLMs such as the decoder-only Llama-3 and the encoder-only RoBERTa. XplainLLM also features a framework for generating grounded explanations and the debugger-scores for multidimensional quality analysis. Our explanations include why-choose and why-not-choose components, reason-elements, and debugger-scores that collectively illuminate the LLM's reasoning behavior. Our evaluations demonstrate XplainLLM's potential to reduce hallucinations and improve grounded explanation generation in LLMs. XplainLLM is a resource for researchers and practitioners to build trust and verify the reliability of LLM outputs.
format Preprint
id arxiv_https___arxiv_org_abs_2311_08614
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs
Chen, Zichen
Chen, Jianda
Singh, Ambuj
Sra, Misha
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) have achieved remarkable success in natural language tasks, yet understanding their reasoning processes remains a significant challenge. We address this by introducing XplainLLM, a dataset accompanying an explanation framework designed to enhance LLM transparency and reliability. Our dataset comprises 24,204 instances where each instance interprets the LLM's reasoning behavior using knowledge graphs (KGs) and graph attention networks (GAT), and includes explanations of LLMs such as the decoder-only Llama-3 and the encoder-only RoBERTa. XplainLLM also features a framework for generating grounded explanations and the debugger-scores for multidimensional quality analysis. Our explanations include why-choose and why-not-choose components, reason-elements, and debugger-scores that collectively illuminate the LLM's reasoning behavior. Our evaluations demonstrate XplainLLM's potential to reduce hallucinations and improve grounded explanation generation in LLMs. XplainLLM is a resource for researchers and practitioners to build trust and verify the reliability of LLM outputs.
title XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2311.08614